Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904106049> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2904106049 abstract "Reinforcement Learning is a successful yet slow technique to train autonomous agents. Option-based solutions can be used to accelerate learning and to transfer learned behaviors across tasks by encapsulating a partial policy. However, commonly these options are specific for a single task, do not take in account similar features between tasks and may not correspond exactly to an optimal behavior when transferred to another task. Therefore, unprincipled transfer might provide bad options to the agent, hampering the learning process. We here propose a way to discover and reuse learned object-oriented options in aprobabilistic way in order to enable better actuation choices to the agent in multiple different tasks. Our experimental evaluation show that our proposal is able to learn and successfully reuse options across different tasks." @default.
- W2904106049 created "2018-12-22" @default.
- W2904106049 creator A5021316298 @default.
- W2904106049 creator A5051450869 @default.
- W2904106049 creator A5053630715 @default.
- W2904106049 creator A5069264027 @default.
- W2904106049 creator A5086613847 @default.
- W2904106049 date "2018-10-01" @default.
- W2904106049 modified "2023-09-30" @default.
- W2904106049 title "A Framework to Discover and Reuse Object-Oriented Options in Reinforcement Learning" @default.
- W2904106049 cites W1949804828 @default.
- W2904106049 cites W2014512216 @default.
- W2904106049 cites W2020573190 @default.
- W2904106049 cites W2031727428 @default.
- W2904106049 cites W2041367235 @default.
- W2904106049 cites W2101355568 @default.
- W2904106049 cites W2109910161 @default.
- W2904106049 cites W2145339207 @default.
- W2904106049 cites W2585821313 @default.
- W2904106049 cites W32403112 @default.
- W2904106049 doi "https://doi.org/10.1109/bracis.2018.00027" @default.
- W2904106049 hasPublicationYear "2018" @default.
- W2904106049 type Work @default.
- W2904106049 sameAs 2904106049 @default.
- W2904106049 citedByCount "1" @default.
- W2904106049 countsByYear W29041060492023 @default.
- W2904106049 crossrefType "proceedings-article" @default.
- W2904106049 hasAuthorship W2904106049A5021316298 @default.
- W2904106049 hasAuthorship W2904106049A5051450869 @default.
- W2904106049 hasAuthorship W2904106049A5053630715 @default.
- W2904106049 hasAuthorship W2904106049A5069264027 @default.
- W2904106049 hasAuthorship W2904106049A5086613847 @default.
- W2904106049 hasConcept C10138342 @default.
- W2904106049 hasConcept C107457646 @default.
- W2904106049 hasConcept C119857082 @default.
- W2904106049 hasConcept C127413603 @default.
- W2904106049 hasConcept C150899416 @default.
- W2904106049 hasConcept C154945302 @default.
- W2904106049 hasConcept C162324750 @default.
- W2904106049 hasConcept C182306322 @default.
- W2904106049 hasConcept C199360897 @default.
- W2904106049 hasConcept C201995342 @default.
- W2904106049 hasConcept C206588197 @default.
- W2904106049 hasConcept C2780451532 @default.
- W2904106049 hasConcept C2781238097 @default.
- W2904106049 hasConcept C41008148 @default.
- W2904106049 hasConcept C548081761 @default.
- W2904106049 hasConcept C97541855 @default.
- W2904106049 hasConcept C98045186 @default.
- W2904106049 hasConceptScore W2904106049C10138342 @default.
- W2904106049 hasConceptScore W2904106049C107457646 @default.
- W2904106049 hasConceptScore W2904106049C119857082 @default.
- W2904106049 hasConceptScore W2904106049C127413603 @default.
- W2904106049 hasConceptScore W2904106049C150899416 @default.
- W2904106049 hasConceptScore W2904106049C154945302 @default.
- W2904106049 hasConceptScore W2904106049C162324750 @default.
- W2904106049 hasConceptScore W2904106049C182306322 @default.
- W2904106049 hasConceptScore W2904106049C199360897 @default.
- W2904106049 hasConceptScore W2904106049C201995342 @default.
- W2904106049 hasConceptScore W2904106049C206588197 @default.
- W2904106049 hasConceptScore W2904106049C2780451532 @default.
- W2904106049 hasConceptScore W2904106049C2781238097 @default.
- W2904106049 hasConceptScore W2904106049C41008148 @default.
- W2904106049 hasConceptScore W2904106049C548081761 @default.
- W2904106049 hasConceptScore W2904106049C97541855 @default.
- W2904106049 hasConceptScore W2904106049C98045186 @default.
- W2904106049 hasLocation W29041060491 @default.
- W2904106049 hasOpenAccess W2904106049 @default.
- W2904106049 hasPrimaryLocation W29041060491 @default.
- W2904106049 hasRelatedWork W2335758940 @default.
- W2904106049 hasRelatedWork W2946016983 @default.
- W2904106049 hasRelatedWork W2960456850 @default.
- W2904106049 hasRelatedWork W3021430260 @default.
- W2904106049 hasRelatedWork W4281645081 @default.
- W2904106049 hasRelatedWork W4308262314 @default.
- W2904106049 hasRelatedWork W4319083788 @default.
- W2904106049 hasRelatedWork W4379662533 @default.
- W2904106049 hasRelatedWork W4382286161 @default.
- W2904106049 hasRelatedWork W4386213806 @default.
- W2904106049 isParatext "false" @default.
- W2904106049 isRetracted "false" @default.
- W2904106049 magId "2904106049" @default.
- W2904106049 workType "article" @default.